def set_algorithm(name, no_obj, setup):
"""
Text.
Args:
name (str): Name of the optimization algorithm.
n_obj (int): Number of objectives.
setup (dict): Optimization setup parameters.
Returns:
algorithm (): Optization algorithm object.
"""
if name == "default":
if no_obj == 1:
name = "ga"
elif no_obj > 1:
name = "nsga3"
# Get settings
setup_gen = load_json(
os.path.join(settings["root"], "app", "config", "opticonf", "general"))
setup_alg = load_json(
os.path.join(settings["root"], "app", "config", "opticonf", name))
algorithm_args = {}
# Get optimization settings objects
algorithm_args["sampling"] = get_sampling(setup_gen["sampling"])
if "operators" in setup:
for operator in setup["operators"]:
algorithm_args[operator] = get_operator(operator, setup)
# Get reference directions
if name == "nsga3":
algorithm_args["ref_dirs"] = get_reference_directions(
"energy", no_obj, setup_alg["ref_dirs_coef"] * no_obj)
# Modify population
if "n_offsprings" in setup:
algorithm_args["n_offsprings"] = setup["n_offsprings"]
if "pop_size" in setup:
algorithm_args["pop_size"] = setup["pop_size"]
algorithm = get_algorithm(name,
eliminate_duplicates=True,
**algorithm_args)
return algorithm
def __init__(self):
super().__init__()
self.ansys_project_folder = settings["data"]["project_folder"]
self.input_param_name = settings["data"]["input_names"]
self.setup = load_json(os.path.join(settings["root"],"app","config","dataconf","ansys"))
self.valid_licences = [name for name in self.setup["licenses"].values()]
def save(self):
"""
Saves the surrogate.
"""
if self.name.startswith("ann"):
self.surrogate.save()
else:
pass
## dump_object("meta",self.surrogate)
status = load_json(os.path.join(settings["folder"], "status"))
to_update = {
"surrogate_trained": True,
"range_out": self.surrogate.range_out.tolist()
}
status.update(to_update)
dump_json(os.path.join(settings["folder"], "status"), status)
def reload_info():
"""
Get information about the problem.
Returns:
range_in (np.array): Input parameter allowable ranges.
dim_in (int): Number of input dimensions.
dim_out (int): Number of output dimensions.
n_constr (int): Number of constraints.
"""
status = load_json(os.path.join(settings["folder"], "status"))
if status["surrogate_trained"]:
range_in, dim_in, dim_out, n_const = np.array(
status["range_in"]
), status["dim_in"], status["dim_out"], status["n_const"]
else:
raise Exception("There is no surrogate to load")
return range_in, dim_in, dim_out, n_const
def reload(self):
"""
Reloads the surrogate.
"""
status = load_json(os.path.join(settings["folder"], "status"))
if "ann" in os.listdir(os.path.join(settings["folder"], "logs")):
from metamod.ANN import ANN ############################################
from tensorflow.keras.models import load_model as load_keras_model ############################################
interp = ANN()
interp.nx = status["dim_in"]
interp.ny = status["dim_out"]
interp.model = load_keras_model(
os.path.join(settings["folder"], "logs", "ann"))
interp.range_out = np.array(status["range_out"])
interp.options["print_global"] = False
self.surrogate = interp
else:
self.surrogate = load_object("meta")[0]
def set_surrogate(name, dim_in, dim_out):
"""
Select the desired surrogate model.
Arguments:
name (str): Name of the surrogate.
dim_in (int): Number of input dimensions.
dim_out (int): Number of output dimensions.
Returns:
surrogate (object): Initialized surrogate model.
Raises:
NameError: If the surrogate is not defined-
"""
# Obtain default settings
setup = load_json(
os.path.join(settings["root"], "app", "config", "metaconf", name))
# Optionaly update with setting specified by the input file
if "setup" in settings["surrogate"].keys():
setup.update(settings["surrogate"]["setup"])
# If the ANN surrogate is used, add it to available options
if name == "ann":
from metamod.ANN_tf import ANN ### import only when actually used, its slow due to tensorflow
available.update({"ann": ANN})
setup.update({"dims": (dim_in, dim_out)})
if name == "ann_pt":
setup.update({"dims": (dim_in, dim_out)})
# Load the actual surrogate
surrogate = available[name](**setup)
# Disable printing during using
surrogate.options["print_global"] = False
return surrogate
Arguments
---------
nt : int
Number of points requested.
Returns
-------
ndarray[nt, nx]
The sampling locations in the input space.
"""
xlimits = self.options["xlimits"]
nx = xlimits.shape[0]
x = halton(nx, nt)
return x
adaptive_methods = load_json(
os.path.join(settings["root"], "app", "config", "dataconf", "adaptive"))
sample_bounds = (-1, 1)
samplings = {
"halton": Halton,
"grid": FullFactorial,
"lhs": LHS,
"random": Random
}